Can Nuanced Language Lead to More Actionable Insights? Exploring the Role of Generative AI in Analytical Narrative Structure

TL;DR

This paper investigates moving beyond simple trend captions by using large language models to enrich analytical narratives along semantic, rhetorical, and pragmatic dimensions. It articulates a framework for describing trends with quantified semantics, hedging, and persuasive language guided by Gricean principles, and demonstrates how prompt-design can yield domain-specific, actionable insights. The main contributions include a taxonomy of linguistic dimensions, connective strategies (temporal, part-whole, comparison, roll-up/drill-down, normalization), and pragmatic guidance for decision support and risk assessment, with implications for data-driven decision making. The approach aims to improve readability, memorability, and actionability of data narratives, with potential impact across analytics, decision support, and risk management domains.

Abstract

Relevant language describing trends in data can be useful for generating summaries to help with readers' takeaways. However, the language employed in these often template-generated summaries tends to be simple, ranging from describing simple statistical information (e.g., extrema and trends) without additional context and richer language to provide actionable insights. Recent advances in Large Language Models (LLMs) have shown promising capabilities in capturing subtle nuances in language when describing information. This workshop paper specifically explores how LLMs can provide more actionable insights when describing trends by focusing on three dimensions of analytical narrative structure: semantic, rhetorical, and pragmatic. Building on prior research that examines visual and linguistic signatures for univariate line charts, we examine how LLMs can further leverage the semantic dimension of analytical narratives using quantified semantics to describe shapes in trends as people intuitively view them. These semantic descriptions help convey insights in a way that leads to a pragmatic outcome, i.e., a call to action, persuasion, warning vs. alert, and situational awareness. Finally, we identify rhetorical implications for how well these generated narratives align with the perceived shape of the data, thereby empowering users to make informed decisions and take meaningful actions based on these data insights.